[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XVTAMWNDNPHX5GDYN2YJY":3,"skill-same:01M78XVTAMWNDNPHX5GDYN2YJY":67},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M78XVTAMWNDNPHX5GDYN2YJY","core-indexing",null,"Use the default h3 string API for point indexing, cell inspection, hierarchy, grid navigation, edges, vertices, local IJ coordinates, measurements, and H3 index validation.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fh3-py\u002Fsub-skills\u002Fcore-indexing\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: core-indexing\ndescription: \"Use the default h3 string API for point indexing, cell inspection,\n  hierarchy, grid navigation, edges, vertices, local IJ coordinates,\n  measurements, and H3 index validation.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Core H3 indexing\n\nUse this route when a user needs to turn a latitude\u002Flongitude into an H3 cell,\ninspect a cell or index, move through the hierarchy or neighboring grid, create\nedges or vertices, use local IJ coordinates, measure spherical quantities, or\nvalidate inputs. The public default is the `h3` string API: scalar indexes are\ncanonical lowercase hexadecimal strings and collections are ordinary Python\nlists unless a function documents an unordered result.\n\n- Coordinate order is always `(lat, lng)` (latitude first, in degrees).\n- H3 resolutions are integers `0..15`; a larger resolution is finer.\n- Validate a cell\u002Findex before expensive navigation or measurement. Predicates\n  return `False` for malformed or wrong-kind values; operational functions\n  raise an H3 exception instead of silently accepting them.\n- Outputs from grid, child, compact, pentagon, and edge enumerations have no\n  guaranteed order unless stated otherwise. Compare them as sets when order is\n  not part of the task.\n- For representation, performance, NumPy\u002Fmemoryview choices, or integer API\n  calls, use [api-variants](..\u002Fapi-variants\u002FSKILL.md); this route stays with\n  default string behavior.\n- For polygon\u002FGeoJSON shape construction or shape-to-cells, use\n  [polygon-geospatial](..\u002Fpolygon-geospatial\u002FSKILL.md).\n- See the [root h3-py route](..\u002F..\u002FSKILL.md) for installation and global\n  routing guidance.\n\n## Standard operating procedure\n\n1. Normalize the task: point(s), target resolution, cell(s), requested relation,\n   measurement unit, and expected output shape.\n2. Use `latlng_to_cell(lat, lng, res)` for a point, then check\n   `is_valid_cell(cell)` and `get_resolution(cell)`.\n3. Before hierarchy\u002Fgrid calls, require cells at the intended resolution and\n   verify that requested parent\u002Fchild resolutions are legal. For a collection,\n   inspect every member; `compact_cells` requires one common resolution.\n4. Use the smallest operation that matches the task: `grid_disk` for filled\n   neighborhoods, `grid_ring` for an exact shell, `grid_path_cells` for an\n   ordered shortest path, and `grid_distance` for a scalar distance.\n5. For a directed edge, confirm `are_neighbor_cells(origin, destination)` or\n   catch `H3NotNeighborsError`; validate the resulting edge separately.\n6. For vertices, use `cell_to_vertexes` rather than assuming six vertices;\n   pentagons have five. For local IJ, keep one origin and the same resolution.\n7. Measure with explicit units (`km`, `m`, `rads`; areas use `km^2`, `m^2`,\n   `rads^2`) when output leaves the immediate call site.\n8. Record the API call, resolution, coordinate order, unit, and any caught\n   exception so a result can be reproduced without the source checkout.\n\n## Quick checks\n\n```python\nimport h3\n\ncell = h3.latlng_to_cell(37.7752702151959, -122.418307270836, 9)\nassert cell == \"8928308280fffff\"\nassert h3.is_valid_index(cell) and h3.is_valid_cell(cell)\nassert h3.get_resolution(cell) == 9\nassert h3.cell_to_latlng(cell)[0] == 37.77670234943567\n```\n\nFor a deterministic package check, run the bundled helper:\n\n```console\npython scripts\u002Fsmoke_core.py --help\npython scripts\u002Fsmoke_core.py check\n```\n\nRead [api-reference.md](references\u002Fapi-reference.md) for the supported surface,\n[workflows.md](references\u002Fworkflows.md) for copyable recipes, and\n[troubleshooting.md](references\u002Ftroubleshooting.md) before retrying a failure.\n\n## Acceptance checklist\n\n- [ ] The input uses `(lat, lng)`, not `(lng, lat)`.\n- [ ] Every cell\u002Fedge\u002Fvertex passed to an operation has the correct kind and\n      passes its corresponding `is_valid_*` predicate.\n- [ ] Resolution transitions are monotonic and within `0..15`.\n- [ ] Grid\u002Fpath operations use same-resolution cells and an affordable `k`.\n- [ ] Collections are not accidentally supplied as one string.\n- [ ] A unit is valid for the requested quantity and is stated in the result.\n- [ ] Pentagon behavior is accounted for where a fixed six-neighbor or\n      six-vertex assumption would be unsafe.\n- [ ] Unordered output is normalized before comparison or serialization.\n\n## Failure recovery\n\n- `H3CellInvalidError`, `H3IndexInvalidError`, or a `False` predicate result:\n  stop and repair the index source; do not coerce a random hexadecimal string.\n- `H3ResDomainError` or `H3ResMismatchError`: inspect both resolutions and\n  choose a parent\u002Fchild target in range; grid paths and local IJ require the\n  same resolution.\n- `H3NotNeighborsError`: test adjacency and reverse the edge direction only\n  when the requested direction is actually intended.\n- `H3FailedError` during distance\u002Flocal IJ\u002Fpath: reduce the geographic span or\n  choose a known same-face neighborhood; the operation can be undefined or\n  too far to compute, not evidence that the indexes are invalid.\n- `ValueError` for a unit: use only the documented units in\n  [api-reference.md](references\u002Fapi-reference.md).\n- Import or missing-package failures: follow the root installation route, then\n  rerun `smoke_core.py check` before diagnosing H3 data.\n","# Core H3 indexing\n\nUse this route when a user needs to turn a latitude\u002Flongitude into an H3 cell,\ninspect a cell or index, move through the hierarchy or neighboring grid, create\nedges or vertices, use local IJ coordinates, measure spherical quantities, or\nvalidate inputs. The public default is the `h3` string API: scalar indexes are\ncanonical lowercase hexadecimal strings and collections are ordinary Python\nlists unless a function documents an unordered result.\n\n- Coordinate order is always `(lat, lng)` (latitude first, in degrees).\n- H3 resolutions are integers `0..15`; a larger resolution is finer.\n- Validate a cell\u002Findex before expensive navigation or measurement. Predicates\n  return `False` for malformed or wrong-kind values; operational functions\n  raise an H3 exception instead of silently accepting them.\n- Outputs from grid, child, compact, pentagon, and edge enumerations have no\n  guaranteed order unless stated otherwise. Compare them as sets when order is\n  not part of the task.\n- For representation, performance, NumPy\u002Fmemoryview choices, or integer API\n  calls, use [api-variants](..\u002Fapi-variants\u002FSKILL.md); this route stays with\n  default string behavior.\n- For polygon\u002FGeoJSON shape construction or shape-to-cells, use\n  [polygon-geospatial](..\u002Fpolygon-geospatial\u002FSKILL.md).\n- See the [root h3-py route](..\u002F..\u002FSKILL.md) for installation and global\n  routing guidance.\n\n## Standard operating procedure\n\n1. Normalize the task: point(s), target resolution, cell(s), requested relation,\n   measurement unit, and expected output shape.\n2. Use `latlng_to_cell(lat, lng, res)` for a point, then check\n   `is_valid_cell(cell)` and `get_resolution(cell)`.\n3. Before hierarchy\u002Fgrid calls, require cells at the intended resolution and\n   verify that requested parent\u002Fchild resolutions are legal. For a collection,\n   inspect every member; `compact_cells` requires one common resolution.\n4. Use the smallest operation that matches the task: `grid_disk` for filled\n   neighborhoods, `grid_ring` for an exact shell, `grid_path_cells` for an\n   ordered shortest path, and `grid_distance` for a scalar distance.\n5. For a directed edge, confirm `are_neighbor_cells(origin, destination)` or\n   catch `H3NotNeighborsError`; validate the resulting edge separately.\n6. For vertices, use `cell_to_vertexes` rather than assuming six vertices;\n   pentagons have five. For local IJ, keep one origin and the same resolution.\n7. Measure with explicit units (`km`, `m`, `rads`; areas use `km^2`, `m^2`,\n   `rads^2`) when output leaves the immediate call site.\n8. Record the API call, resolution, coordinate order, unit, and any caught\n   exception so a result can be reproduced without the source checkout.\n\n## Quick checks\n\n```python\nimport h3\n\ncell = h3.latlng_to_cell(37.7752702151959, -122.418307270836, 9)\nassert cell == \"8928308280fffff\"\nassert h3.is_valid_index(cell) and h3.is_valid_cell(cell)\nassert h3.get_resolution(cell) == 9\nassert h3.cell_to_latlng(cell)[0] == 37.77670234943567\n```\n\nFor a deterministic package check, run the bundled helper:\n\n```console\npython scripts\u002Fsmoke_core.py --help\npython scripts\u002Fsmoke_core.py check\n```\n\nRead [api-reference.md](references\u002Fapi-reference.md) for the supported surface,\n[workflows.md](references\u002Fworkflows.md) for copyable recipes, and\n[troubleshooting.md](references\u002Ftroubleshooting.md) before retrying a failure.\n\n## Acceptance checklist\n\n- [ ] The input uses `(lat, lng)`, not `(lng, lat)`.\n- [ ] Every cell\u002Fedge\u002Fvertex passed to an operation has the correct kind and\n      passes its corresponding `is_valid_*` predicate.\n- [ ] Resolution transitions are monotonic and within `0..15`.\n- [ ] Grid\u002Fpath operations use same-resolution cells and an affordable `k`.\n- [ ] Collections are not accidentally supplied as one string.\n- [ ] A unit is valid for the requested quantity and is stated in the result.\n- [ ] Pentagon behavior is accounted for where a fixed six-neighbor or\n      six-vertex assumption would be unsafe.\n- [ ] Unordered output is normalized before comparison or serialization.\n\n## Failure recovery\n\n- `H3CellInvalidError`, `H3IndexInvalidError`, or a `False` predicate result:\n  stop and repair the index source; do not coerce a random hexadecimal string.\n- `H3ResDomainError` or `H3ResMismatchError`: inspect both resolutions and\n  choose a parent\u002Fchild target in range; grid paths and local IJ require the\n  same resolution.\n- `H3NotNeighborsError`: test adjacency and reverse the edge direction only\n  when the requested direction is actually intended.\n- `H3FailedError` during distance\u002Flocal IJ\u002Fpath: reduce the geographic span or\n  choose a known same-face neighborhood; the operation can be undefined or\n  too far to compute, not evidence that the indexes are invalid.\n- `ValueError` for a unit: use only the documented units in\n  [api-reference.md](references\u002Fapi-reference.md).\n- Import or missing-package failures: follow the root installation route, then\n  rerun `smoke_core.py check` before diagnosing H3 data.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fh3-py\u002Fsub-skills\u002Fcore-indexing",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill core-indexing",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill core-indexing",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill core-indexing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fh3-py\u002Fsub-skills\u002Fcore-indexing\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",8880,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fh3-py\u002Fsub-skills\u002Fcore-indexing\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",7923,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fh3-py\u002Fsub-skills\u002Fcore-indexing\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",6831,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fh3-py\u002Fsub-skills\u002Fcore-indexing\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fsmoke_core.py","SCRIPT","脚本",2054,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fh3-py\u002Fsub-skills\u002Fcore-indexing\u002Fscripts\u002Fsmoke_core.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]